Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered; the description adds value beyond that with ordering ('newest first') and the shape of each returned item, including thread-specific fields like part count and media_count. It does not discuss pagination behavior or result-size limits itself, leaving that to the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the definition and ordering, then the return shape, then the routing advice — a sensible order with no filler. The return-field enumeration is slightly list-like and a touch long, but with no output schema present it is doing real work rather than padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, and the description compensates by describing the returned fields, including the thread-specific detail. Combined with annotations covering the safety profile and a schema that fully documents all three optional parameters, an agent has everything needed to select and call this correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so page, limit and social_set are already fully documented with defaults and bounds, and the baseline of 3 applies. The description adds no filtering or paging semantics of its own; the only identifier it references (`id`) is an output field used as input to the sibling tool, not one of this tool's parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource (get the user's saved drafts) and pins down the object precisely: posts kept but not scheduled or published, returned newest first. It also places the resource in the product hierarchy (Plan → Posts → Drafts in SupaBird), so an agent can distinguish it from adjacent surfaces without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit next step ('To schedule one, call schedule_saved_post with that `id` and a scheduled_date, or next_free_slot: true') and an explicit exclusion with the alternative named ('Saved ideas from Ideas Lab, Video to Posts, Rewrite, and Content Machine are listed by get_saved_ideas instead'). Both the when-to-use and the when-not-to-use path are spelled out.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.